Killed: 9 (SIGKILL / OOM killer)
The kernel terminated Claude Code outright, usually for memory pressure.
368 issues · 73 open · 295 resolved (80%) · first seen Feb 25, 2025
First response · local
What to do now
Most likely: The local Claude Code process crashed while parsing or executing.
- Record the Claude Code version and the first stack frame before restarting.
- Try a fresh session with the same minimal input to distinguish corrupted state from a repeatable crash.
- Preserve logs and compare reports from the same version before downgrading.
These are conservative triage steps, not an official Anthropic fix. Use the issue and workaround evidence below before making a destructive configuration change.
Is this getting better or worse?
This class of problem is holding steady. 122 new reports in the last 90 days vs 106 in the 90 before — +15%. The open backlog peaked at 105 in 2026-08 and sits at 73 today.
Derived by counting each matching issue from its creation date until it closed. First-party
computation over the anthropics/claude-code tracker — the trend is not published
anywhere upstream.
Which builds report this
252 of these reports name the Claude Code build they were running, spanning 129 releases. Heaviest reporters:
- Claude Code v2.1.220
- Claude Code v2.1.233
- Claude Code v2.1.205
- Claude Code v2.1.246
- Claude Code v2.1.231
- Claude Code v2.1.226
- Claude Code v2.1.170
- Claude Code v2.1.160
Report volume, not a defect count: an issue can mention a build without that build having caused the failure. Versions come from the version string in the bug-report template, matched against real published tags.
Do these get fixed?
Median time to close is 29 days across 295 closures. Of the 295 closures with a recorded reason, 15% were closed as completed and 252 as not-planned or duplicate. The most recent completed fix landed in 2026-10.
Workarounds reported by the community
183 of these issues post a workaround someone says worked. The highest-engagement ones:
- Claude.ai MCP servers auto-injected into Claude Code without opt-in — causes OOM crashes on resource-constrained systems
- …r's Claude.ai account and load them into every CLI session. Workaround Manually editing to set: However, this is a cached flag and may be overwritten on next update/startup. Expected Behavior 1. This should be opt-in, no…
Found in the description of #20412 · resolved - [BUG] Critical memory regression in 2.1.27 - OOM crash on simple input
- …toring during 2.1.27 session 2.1.25 after rollback (stable) Workaround Roll back to 2.1.25: Environment Info - Platform: Linux (Ubuntu 24.04, kernel 6.8.0-90-generic) - Architecture: x86 64 (QEMU/KVM VM) - RAM: 8GB + 4GB…
Found in the description of #22042 · resolved - Claude Code Memory Leak - Process Grows to 120+ GB RAM and Gets OOM Killed
- …d data structures (conversation history, file caches, etc.) Workaround Currently, the only workaround is to periodically restart Claude Code before memory exhaustion occurs, which is highly disruptive to workflow. --- Pr…
Found in the description of #4953 · still open - Critical Memory Leak: Claude Code Consumed 129GB RAM and Caused System Freeze
- …there's unbounded caching 5. Review event listener cleanup Workaround Currently monitoring with: Plan to restart Claude Code when memory usage exceeds safe threshold.
Found in the description of #11315 · still open - [BUG] Memory leak in long-running idle Claude Code sessions
- Not a fix for the leak, but a workaround that helped me live with it: unload the idle sessions and resume them later. I packaged that as an open-source plugin, It shows how much memory each session's process tree holds,…
Found in the thread of #18859 · still open
Excerpts are quoted from the linked issue so you can judge relevance before opening it. Threads that only ask for a workaround, or report that there is none, are excluded. These are community suggestions, not official guidance from Anthropic — read the full thread before applying one.
Matching issues 1–100
Ranked by community engagement (reactions weighted over comments). Listing the top 300 of 368 matches; the statistics above cover all 368.
- Claude.ai MCP servers auto-injected into Claude Code without opt-in — causes OOM crashes on resource-constrained systems
- [BUG] Critical memory regression in 2.1.27 - OOM crash on simple input
- Claude Code Memory Leak - Process Grows to 120+ GB RAM and Gets OOM Killed
- Critical Memory Leak: Claude Code Consumed 129GB RAM and Caused System Freeze
- [BUG] Memory leak in long-running idle Claude Code sessions
- [BUG] claude starts and 3 seconds later exits.
- Background process termination crashes Claude Code in Docker containers
- Claude Code freezes: static spinner, unresponsive input, ignores SIGTERM
- Bundled ugrep OOMs the host: -E with two bounded {0,N} intervals explodes DFA construction to multiple GB
- Scroll back + Color bleaching + Memory leak fix -- npm i -g claudefix --- Cons: Plugs myself and runs an ad, makes claude immutable so it stays locked --- Slowly adding more festures to ennhance UX, youre a bot if youre bitching about safety in the comments.. Linux only
- [BUG] Session usage meter accruing at impossible rate — Max plan, single + multi-session usage
- [Bug] Ink renderer crashes in spawned teammate agents during tmux mode sessions
- [BUG] macOS: sleep inhibitor SIGKILLs its caffeinate before spawning the replacement — Mac idle-sleeps mid-task once the display is off
- Claude Code freezes during API call ("Befuddling" spinner), terminal becomes completely unresponsive
- [BUG] Segmentation fault (SIGSEGV) on install and startup — CachyOS Linux
- [BUG] v2.1.87 idle process grows ~500 MB/min, OOM-killed within minutes on 16GB WSL2 system
- [FEATURE] Built-in Session Manager (claude sessions) — Consolidates 14+ Orphan/Process Issues
- [FEATURE] Add `maxParallelAgents` Configuration Setting
- [BUG] Claude Code spawned ~3,000 parallel bash processes in 17 seconds, causing OOM crash and hard reboot.
- Telegram plugin: bun server.ts stuck at 99% CPU in idle loop
- Bug: Memory leak causing OOM kill on Linux (15-17GB memory consumption)
- [BUG] Claude Code VS Code extension leaks worker processes when creating new chats
- Bash tool falsely reports 'temp filesystem … is full (0MB free)' on any empty-stdout + non-zero-exit command
- Background processes started by Bash tool are not cleaned up on session exit
- [Bug] Background tasks killed without TaskStop when session goes idle
- [BUG] install.sh OOM killed on 8 GB Debian VM — Node.js SEA binary consumes 7.5 GB RAM
- [BUG] v2.1.111: ESC during MCP tool call kills all Python stdio MCPs (regression from v2.1.104, 30-line repro) PLEASE FIX NOW!
- Bundled ugrep runs with no memory limit or timeout — model-generated regex consumed 13.6 GB and thrashed the host
- [BUG] Claude code is killed by OOM killer due to subprocess issue
- [PROPOSAL] Golang Rewrite to Address Critical Memory Usage (1.5-2GB per session)
- [BUG] Claude Code crashes with SIGABRT during shutdown due to MCP server termination failure
- Scheduled tasks and background sub-agents leak processes/UI state without cleanup
- [BUG] Session files grow unboundedly, causing OOM crash on startup ("Aborted (core dumped)")
- [BUG]: /mcp modal becomes unresponsive to all keys (arrows, Enter, Esc, Ctrl-C) — regression in 2.1.118/2.1.119
- Single Claude process consumed 36 GB on 18 GB machine, triggering Jetsam OOM kill (v2.1.37)
- [BUG] Memory leak causes repeated OOM kills in v2.1.224 (14.5GB and 21.3GB anon-rss, two incidents same day)
- [BUG] Task tool subagent processes not terminated after parent session ends (Linux)
- Background tasks mass-killed by memory-pressure reaper on Linux hosts with low MemFree but high MemAvailable (PSI ~0)
- OOM crash under multi-subagent load: subagent CLI processes grow to ~6.5 GB RSS each; CliGovernor logs critical memory pressure for 8 min but evicts nothing (Linux, Desktop 1.17377.0 / CLI 2.1.187)
- [BUG] Claude Code CLI freezes and becomes unresponsive (SIGKILL required)
- [CRITICAL] MCP Server Causes 16+ Hour Hang - No Timeout or Stuck Detection
- [FEATURE] Advanced Process Control and Interaction for Background Commands
- [BUG] ~/.claude.json.tmp.<pid>.<hash> atomic-write leftovers are never reclaimed by the retention sweep
- Background bash children survive session close; task-output files have no size cap (4.86 TB runaway on Windows)
- Orphaned Claude session survives 11h after worktree deletion, ignores SIGTERM
- [BUG] Claude Code freezes when Terminal.app menu bar / toolbar is activated (macOS)
- Channel plugin subprocesses (bun server.ts) leak across sessions — not killed on session exit
- Background task respawns infinitely when command hangs, causing fork bomb
- Memory leak: idle sessions consume excessive RAM (27GB+)
- Claude Desktop (Windows): heavy ad-stack page in in-app Claude Browser pane crashes entire app, no crash dump, kills all hosted sessions
- [BUG] Kernel OOM (not V8 heap) from parallel subagent + per-agent MCP fan-out exhausts host RAM
- [BUG] Mac app: orphaned claude-code CLI from ccd_session chaptered sub-task spins at 100% CPU indefinitely after parent exits non-gracefully
- [BUG] Shell snapshot captures mise functions without `__MISE_EXE` variable, causing infinite fork recursion and OOM
- MCP stdio servers reported as 'failed' on exit despite clean shutdown
- [BUG] sandbox Claude Code crashes and OOM-killed by kernel when node_modules exists in project directory
- [BUG] Memory leak + Swap growth — Claude Code Sonnet 4.6 kills sessions in ~8 min (v2.1.49)
- Memory Leak: VmPeak reaches 135GB, causes OOM kill
- Embedded ugrep in the Bash grep shim allocates ~29 GB compiling `.{0,N}(a|b|c).{0,M}`, OOM-kills the host
- PowerShell script blocks / subexpressions still bypass allowlist and prompt (re-file of #52926, stale-bot closed)
- Claude Code causes 49GB invisible kernel memory allocation, triggers OOM killer on 128GB system
- Process stuck in emoji width calculation loop (high CPU, unresponsive)
- Scrollback + Debounce + Colors Fix - Glitching and Color Bleaching - All Fixes Optional - Anthropic Hire Me Challenge - IMPOSSIBLE?!
- [BUG] Claude Code v1.0.53 allocating >120GB VM and 44GB physical memory and getting OOM killed
- Bash-tool `grep` shim (ugrep emulation): catastrophic backtracking — 6.6 GB RSS / OOM kill on a 20 KB file
- Transcript JSONL corruption; records spliced by unsynchronized writers
- [BUG] SGR mouse-tracking sequences leak into the prompt input again on 2.1.220 (Apple Terminal) — regression of #58653 / #49017
- Single background subagent (run_in_background, no tool use) balloons to 9.5 GiB in ~100 s → global kernel OOM (2.1.220, Linux, no swap)
- [BUG] Embedded ugrep OOMs on bounded-repeat regex while Bash grep is silently shadowed (Linux, 2.1.205-2.1.212)
- Bash tool: grep→ugrep shim children not killed on timeout; runaway memory (100+ GB) on long-line files
- [BUG] FleetView (`claude agents`) remote session entry persists on Code tab after TUI exits (zombie entries, no cleanup on relay disconnect)
- Claude Desktop silently disconnects remote MCP servers (mcp-remote) and fails to auto-relaunch
- [BUG] Claude Code binary rejected by macOS 26 Gatekeeper — SIGKILL on 2nd concurrent instance
- CLI session unexpectedly resets when spawning 3 parallel Agent subagents
- MCP plugin bun processes orphaned on unclean exit, peg CPU at 100% each
- remote-control: Environment expires server-side after ~10 min, no auto-reconnect
- [BUG] Cowork crashes on startup: apply-seccomp Killed in VM sandbox (macOS ARM64)
- Chrome extension MCP process becomes stale mid-session, kill deregisters tools permanently
- Bug: Claude Code process hangs with 100% CPU usage (requires kill -9)
- [BUG] Complete UI freeze during Bash tool execution - Thread deadlock
- [BUG] Version 2.0.58 crashes and freezes
- [BUG] 2.1.284 freezes on first Enter: new sandbox glob expander synchronously walks all of ~ for "~/**/…" denyRead patterns (follows symlinks, unbounded memory); 2.1.280 fine
- [BUG] Bash teardown can SIGKILL an unrelated process after PID reuse
- Background Bash tasks (run_in_background) killed mid-run silently — no OOM, not user-initiated; setsid-detached processes immune
- Bundled ugrep allocates 4-17 GB to search a 64 KB file when the pattern has a trailing `.{N}` bound (Linux/WSL2, 2.1.214)
- SessionEnd hook killed before completing on exit ("Hook cancelled") — EXIT trap never runs, no configurable grace [2.1.187, tui: fullscreen]
- [BUG] Claude Desktop force-quits within seconds of opening the Code tab (CPU ~120%, no crash log) — macOS, regression after 2026-06-18 update
- Feature request: AZ5 emergency stop — immediately kill all running tasks and commands
- Suspected Node.js subprocess leak in v2.1.160 — ~115 node processes exhaust RAM, trigger system-wide OOM
- `claude -p` does not exit after final text when session used `run_in_background=True` Bash tools, even after those processes complete naturally
- claude.exe ugrep subprocess wedges holding 6-9 GB RAM; parent does not SIGKILL on timeout
- claude --print long-running sessions hang post-completion until SIGKILL (cc 2.1.133.6c0)
- False positive "Blocked by endpoint security" SIGKILL screen on clean personal Mac (no MDM/EDR)
- Cowork: gvisor network daemon stalls at AcceptBess on every VM boot, causing immediate keepalive failure and session termination
- Telegram plugin: zombie bun processes cause 409 Conflict — process.ppid cached in bun runtime
- [BUG] Claude Code kills ALL Python processes system-wide at turn boundaries (Windows)
- [Bug] CLI crashes on session resume: synchronous JS pass blocks event loop, accumulates 7–11 GB RSS, then crashes with tengu_uncaught_exception cascade
- [Feature] Agent Teams: Set higher oom_score_adj on teammate agents than on the lead/orchestrator
- Interactive TUI crashes: screen width spirals unboundedly (100% write ratio)
- [BUG] Memory regression in v2.1.62: Claude process consuming ~6.4GB RAM on 6.5GB system, causing repeated OOM kills
- [FEATURE] Rotate session JSONL files at compaction boundaries